argus-screen
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SCREEN_API_KEY | Yes | Your Screen Terminal API key, sent in the X-API-Key header. Required to run the MCP server; each screened name uses one screen from your key. | |
| SCREEN_API_URL | No | Overrides the base URL of the Screen Terminal API. Defaults to https://screen.unbackoffice.com. | https://screen.unbackoffice.com |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| screen_nameA | Screen one name against PEP, sanctions, entity, enforcement and watchlist records via Screen Terminal (POST /v1/screen). Returns result_band (strong, possible, weak or none), the per-type bands (sanctions_band, pep_band, watchlist_band) and the top matches. Route on the per-type bands, not result_band alone. Uses one screen from the key's quota. A match is a lead for review, not a finding. |
| screen_batchA | Screen up to 50 names in one call (POST /v1/screen/batch). Each name uses one screen; a batch is all or nothing, so if the key cannot cover every name nothing is screened. Returns counts and, per name in order, the bands and top matches. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools are clearly differentiated: screen_name handles one name, while screen_batch handles up to 50 names in a single call. Their descriptions explicitly state the scope and endpoint, leaving no plausible confusion about which tool to use.
Both names follow a consistent snake_case pattern with the shared `screen_` prefix. The suffixes distinguish single-name versus batch operations predictably.
Two tools are reasonable for a narrow screening API, with a clean single-versus-batch split. However, the surface is quite thin and could feel limited if agents expect quota checks or a way to retrieve prior screening results.
The core screening workflow is covered for both individual and bulk names, including result bands and top matches. Minor gaps remain, such as checking remaining quota, retrieving a prior screening by ID, or handling batch status separately.